From 4670fd819e7f47392c7c6fc6168ea2857c66d163 Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Sat, 9 Jun 2012 01:25:47 -0700
Subject: tcp: Get rid of inetpeer special cases.

The get_peer method TCP uses is full of special cases that make no
sense accommodating, and it also gets in the way of doing more
reasonable things here.

First of all, if the socket doesn't have a usable cached route, there
is no sense in trying to optimize timewait recycling.

Likewise for the case where we have IP options, such as SRR enabled,
that make the IP header destination address (and thus the destination
address of the route key) differ from that of the connection's
destination address.

Just return a NULL peer in these cases, and thus we're also able to
get rid of the clumsy inetpeer release logic.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_minisocks.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

(limited to 'net/ipv4/tcp_minisocks.c')

diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index b85d9fe7d66..fef9dbf3af0 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -60,9 +60,8 @@ static bool tcp_remember_stamp(struct sock *sk)
 	const struct inet_connection_sock *icsk = inet_csk(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct inet_peer *peer;
-	bool release_it;
 
-	peer = icsk->icsk_af_ops->get_peer(sk, &release_it);
+	peer = icsk->icsk_af_ops->get_peer(sk);
 	if (peer) {
 		if ((s32)(peer->tcp_ts - tp->rx_opt.ts_recent) <= 0 ||
 		    ((u32)get_seconds() - peer->tcp_ts_stamp > TCP_PAWS_MSL &&
@@ -70,8 +69,6 @@ static bool tcp_remember_stamp(struct sock *sk)
 			peer->tcp_ts_stamp = (u32)tp->rx_opt.ts_recent_stamp;
 			peer->tcp_ts = tp->rx_opt.ts_recent;
 		}
-		if (release_it)
-			inet_putpeer(peer);
 		return true;
 	}
 
-- 
cgit v1.2.3-70-g09d2


From 2397849baa7c44c242e5d5142d5d16d1e7ed53d0 Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Sat, 9 Jun 2012 14:56:12 -0700
Subject: [PATCH] tcp: Cache inetpeer in timewait socket, and only when
 necessary.

Since it's guarenteed that we will access the inetpeer if we're trying
to do timewait recycling and TCP options were enabled on the
connection, just cache the peer in the timewait socket.

In the future, inetpeer lookups will be context dependent (per routing
realm), and this helps facilitate that as well.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/tcp.h         |  3 ++-
 include/net/tcp.h           |  1 -
 include/net/timewait_sock.h |  8 --------
 net/ipv4/tcp_ipv4.c         | 10 ----------
 net/ipv4/tcp_minisocks.c    | 27 ++++++++++++++++++++-------
 net/ipv6/tcp_ipv6.c         | 13 -------------
 6 files changed, 22 insertions(+), 40 deletions(-)

(limited to 'net/ipv4/tcp_minisocks.c')

diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index 4c5b6328337..23e8234f75a 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -506,8 +506,9 @@ struct tcp_timewait_sock {
 	u32			  tw_rcv_wnd;
 	u32			  tw_ts_recent;
 	long			  tw_ts_recent_stamp;
+	struct inet_peer	  *tw_peer;
 #ifdef CONFIG_TCP_MD5SIG
-	struct tcp_md5sig_key	*tw_md5_key;
+	struct tcp_md5sig_key	  *tw_md5_key;
 #endif
 	/* Few sockets in timewait have cookies; in that case, then this
 	 * object holds a reference to them (tw_cookie_values->kref).
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 42459186603..9332f342259 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -328,7 +328,6 @@ extern void tcp_shutdown (struct sock *sk, int how);
 extern int tcp_v4_rcv(struct sk_buff *skb);
 
 extern struct inet_peer *tcp_v4_get_peer(struct sock *sk);
-extern void *tcp_v4_tw_get_peer(struct sock *sk);
 extern int tcp_v4_tw_remember_stamp(struct inet_timewait_sock *tw);
 extern int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 		       size_t size);
diff --git a/include/net/timewait_sock.h b/include/net/timewait_sock.h
index 8d6689cb2c6..68f0ecad6c6 100644
--- a/include/net/timewait_sock.h
+++ b/include/net/timewait_sock.h
@@ -22,7 +22,6 @@ struct timewait_sock_ops {
 	int		(*twsk_unique)(struct sock *sk,
 				       struct sock *sktw, void *twp);
 	void		(*twsk_destructor)(struct sock *sk);
-	void		*(*twsk_getpeer)(struct sock *sk);
 };
 
 static inline int twsk_unique(struct sock *sk, struct sock *sktw, void *twp)
@@ -41,11 +40,4 @@ static inline void twsk_destructor(struct sock *sk)
 		sk->sk_prot->twsk_prot->twsk_destructor(sk);
 }
 
-static inline void *twsk_getpeer(struct sock *sk)
-{
-	if (sk->sk_prot->twsk_prot->twsk_getpeer)
-		return sk->sk_prot->twsk_prot->twsk_getpeer(sk);
-	return NULL;
-}
-
 #endif /* _TIMEWAIT_SOCK_H */
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 77f049d00db..fda2ca17135 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1835,20 +1835,10 @@ struct inet_peer *tcp_v4_get_peer(struct sock *sk)
 }
 EXPORT_SYMBOL(tcp_v4_get_peer);
 
-void *tcp_v4_tw_get_peer(struct sock *sk)
-{
-	const struct inet_timewait_sock *tw = inet_twsk(sk);
-	struct net *net = sock_net(sk);
-
-	return inet_getpeer_v4(net, tw->tw_daddr, 1);
-}
-EXPORT_SYMBOL(tcp_v4_tw_get_peer);
-
 static struct timewait_sock_ops tcp_timewait_sock_ops = {
 	.twsk_obj_size	= sizeof(struct tcp_timewait_sock),
 	.twsk_unique	= tcp_twsk_unique,
 	.twsk_destructor= tcp_twsk_destructor,
-	.twsk_getpeer	= tcp_v4_tw_get_peer,
 };
 
 const struct inet_connection_sock_af_ops ipv4_specific = {
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index fef9dbf3af0..cb015317c9f 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -77,20 +77,19 @@ static bool tcp_remember_stamp(struct sock *sk)
 
 static bool tcp_tw_remember_stamp(struct inet_timewait_sock *tw)
 {
+	const struct tcp_timewait_sock *tcptw;
 	struct sock *sk = (struct sock *) tw;
 	struct inet_peer *peer;
 
-	peer = twsk_getpeer(sk);
+	tcptw = tcp_twsk(sk);
+	peer = tcptw->tw_peer;
 	if (peer) {
-		const struct tcp_timewait_sock *tcptw = tcp_twsk(sk);
-
 		if ((s32)(peer->tcp_ts - tcptw->tw_ts_recent) <= 0 ||
 		    ((u32)get_seconds() - peer->tcp_ts_stamp > TCP_PAWS_MSL &&
 		     peer->tcp_ts_stamp <= (u32)tcptw->tw_ts_recent_stamp)) {
 			peer->tcp_ts_stamp = (u32)tcptw->tw_ts_recent_stamp;
 			peer->tcp_ts	   = tcptw->tw_ts_recent;
 		}
-		inet_putpeer(peer);
 		return true;
 	}
 	return false;
@@ -314,9 +313,12 @@ void tcp_time_wait(struct sock *sk, int state, int timeo)
 	const struct inet_connection_sock *icsk = inet_csk(sk);
 	const struct tcp_sock *tp = tcp_sk(sk);
 	bool recycle_ok = false;
+	bool recycle_on = false;
 
-	if (tcp_death_row.sysctl_tw_recycle && tp->rx_opt.ts_recent_stamp)
+	if (tcp_death_row.sysctl_tw_recycle && tp->rx_opt.ts_recent_stamp) {
 		recycle_ok = tcp_remember_stamp(sk);
+		recycle_on = true;
+	}
 
 	if (tcp_death_row.tw_count < tcp_death_row.sysctl_max_tw_buckets)
 		tw = inet_twsk_alloc(sk, state);
@@ -324,8 +326,10 @@ void tcp_time_wait(struct sock *sk, int state, int timeo)
 	if (tw != NULL) {
 		struct tcp_timewait_sock *tcptw = tcp_twsk((struct sock *)tw);
 		const int rto = (icsk->icsk_rto << 2) - (icsk->icsk_rto >> 1);
+		struct inet_sock *inet = inet_sk(sk);
+		struct inet_peer *peer = NULL;
 
-		tw->tw_transparent	= inet_sk(sk)->transparent;
+		tw->tw_transparent	= inet->transparent;
 		tw->tw_rcv_wscale	= tp->rx_opt.rcv_wscale;
 		tcptw->tw_rcv_nxt	= tp->rcv_nxt;
 		tcptw->tw_snd_nxt	= tp->snd_nxt;
@@ -347,6 +351,12 @@ void tcp_time_wait(struct sock *sk, int state, int timeo)
 		}
 #endif
 
+		if (recycle_on)
+			peer = icsk->icsk_af_ops->get_peer(sk);
+		tcptw->tw_peer = peer;
+		if (peer)
+			atomic_inc(&peer->refcnt);
+
 #ifdef CONFIG_TCP_MD5SIG
 		/*
 		 * The timewait bucket does not have the key DB from the
@@ -398,8 +408,11 @@ void tcp_time_wait(struct sock *sk, int state, int timeo)
 
 void tcp_twsk_destructor(struct sock *sk)
 {
-#ifdef CONFIG_TCP_MD5SIG
 	struct tcp_timewait_sock *twsk = tcp_twsk(sk);
+
+	if (twsk->tw_peer)
+		inet_putpeer(twsk->tw_peer);
+#ifdef CONFIG_TCP_MD5SIG
 	if (twsk->tw_md5_key) {
 		tcp_free_md5sig_pool();
 		kfree_rcu(twsk->tw_md5_key, rcu);
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index b5ecf37b61a..f91b0bfd12d 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1746,23 +1746,10 @@ static struct inet_peer *tcp_v6_get_peer(struct sock *sk)
 	return rt6_get_peer_create(rt);
 }
 
-static void *tcp_v6_tw_get_peer(struct sock *sk)
-{
-	const struct inet6_timewait_sock *tw6 = inet6_twsk(sk);
-	const struct inet_timewait_sock *tw = inet_twsk(sk);
-	struct net *net = sock_net(sk);
-
-	if (tw->tw_family == AF_INET)
-		return tcp_v4_tw_get_peer(sk);
-
-	return inet_getpeer_v6(net, &tw6->tw_v6_daddr, 1);
-}
-
 static struct timewait_sock_ops tcp6_timewait_sock_ops = {
 	.twsk_obj_size	= sizeof(struct tcp6_timewait_sock),
 	.twsk_unique	= tcp_twsk_unique,
 	.twsk_destructor= tcp_twsk_destructor,
-	.twsk_getpeer	= tcp_v6_tw_get_peer,
 };
 
 static const struct inet_connection_sock_af_ops ipv6_specific = {
-- 
cgit v1.2.3-70-g09d2


From 41063e9dd11956f2d285e12e4342e1d232ba0ea2 Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Tue, 19 Jun 2012 21:22:05 -0700
Subject: ipv4: Early TCP socket demux.

Input packet processing for local sockets involves two major demuxes.
One for the route and one for the socket.

But we can optimize this down to one demux for certain kinds of local
sockets.

Currently we only do this for established TCP sockets, but it could
at least in theory be expanded to other kinds of connections.

If a TCP socket is established then it's identity is fully specified.

This means that whatever input route was used during the three-way
handshake must work equally well for the rest of the connection since
the keys will not change.

Once we move to established state, we cache the receive packet's input
route to use later.

Like the existing cached route in sk->sk_dst_cache used for output
packets, we have to check for route invalidations using dst->obsolete
and dst->ops->check().

Early demux occurs outside of a socket locked section, so when a route
invalidation occurs we defer the fixup of sk->sk_rx_dst until we are
actually inside of established state packet processing and thus have
the socket locked.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/inet_hashtables.h |  4 ++--
 include/net/protocol.h        |  1 +
 include/net/sock.h            |  2 ++
 include/net/tcp.h             |  1 +
 net/core/sock.c               |  5 +++++
 net/ipv4/af_inet.c            | 18 +++++++++--------
 net/ipv4/ip_input.c           | 39 ++++++++++++++++++++++++------------
 net/ipv4/tcp_input.c          | 16 ++++++++++++++-
 net/ipv4/tcp_ipv4.c           | 46 +++++++++++++++++++++++++++++++++++++++++++
 net/ipv4/tcp_minisocks.c      |  2 ++
 10 files changed, 110 insertions(+), 24 deletions(-)

(limited to 'net/ipv4/tcp_minisocks.c')

diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h
index 808fc5f76b0..54be0287eb9 100644
--- a/include/net/inet_hashtables.h
+++ b/include/net/inet_hashtables.h
@@ -379,10 +379,10 @@ static inline struct sock *__inet_lookup_skb(struct inet_hashinfo *hashinfo,
 					     const __be16 sport,
 					     const __be16 dport)
 {
-	struct sock *sk;
+	struct sock *sk = skb_steal_sock(skb);
 	const struct iphdr *iph = ip_hdr(skb);
 
-	if (unlikely(sk = skb_steal_sock(skb)))
+	if (sk)
 		return sk;
 	else
 		return __inet_lookup(dev_net(skb_dst(skb)->dev), hashinfo,
diff --git a/include/net/protocol.h b/include/net/protocol.h
index a1b1b530c33..967b926cbfb 100644
--- a/include/net/protocol.h
+++ b/include/net/protocol.h
@@ -37,6 +37,7 @@
 
 /* This is used to register protocols. */
 struct net_protocol {
+	int			(*early_demux)(struct sk_buff *skb);
 	int			(*handler)(struct sk_buff *skb);
 	void			(*err_handler)(struct sk_buff *skb, u32 info);
 	int			(*gso_send_check)(struct sk_buff *skb);
diff --git a/include/net/sock.h b/include/net/sock.h
index 4a452169956..87b424ae750 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -319,6 +319,7 @@ struct sock {
 	unsigned long 		sk_flags;
 	struct dst_entry	*sk_dst_cache;
 	spinlock_t		sk_dst_lock;
+	struct dst_entry	*sk_rx_dst;
 	atomic_t		sk_wmem_alloc;
 	atomic_t		sk_omem_alloc;
 	int			sk_sndbuf;
@@ -1426,6 +1427,7 @@ extern struct sk_buff		*sock_rmalloc(struct sock *sk,
 					      gfp_t priority);
 extern void			sock_wfree(struct sk_buff *skb);
 extern void			sock_rfree(struct sk_buff *skb);
+extern void			sock_edemux(struct sk_buff *skb);
 
 extern int			sock_setsockopt(struct socket *sock, int level,
 						int op, char __user *optval,
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 9332f342259..6660ffc4963 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -325,6 +325,7 @@ extern void tcp_v4_err(struct sk_buff *skb, u32);
 
 extern void tcp_shutdown (struct sock *sk, int how);
 
+extern int tcp_v4_early_demux(struct sk_buff *skb);
 extern int tcp_v4_rcv(struct sk_buff *skb);
 
 extern struct inet_peer *tcp_v4_get_peer(struct sock *sk);
diff --git a/net/core/sock.c b/net/core/sock.c
index 9e5b71fda6e..929bdcc2383 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1465,6 +1465,11 @@ void sock_rfree(struct sk_buff *skb)
 }
 EXPORT_SYMBOL(sock_rfree);
 
+void sock_edemux(struct sk_buff *skb)
+{
+	sock_put(skb->sk);
+}
+EXPORT_SYMBOL(sock_edemux);
 
 int sock_i_uid(struct sock *sk)
 {
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 85a3b176313..07a02f6e969 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -157,6 +157,7 @@ void inet_sock_destruct(struct sock *sk)
 
 	kfree(rcu_dereference_protected(inet->inet_opt, 1));
 	dst_release(rcu_dereference_check(sk->sk_dst_cache, 1));
+	dst_release(sk->sk_rx_dst);
 	sk_refcnt_debug_dec(sk);
 }
 EXPORT_SYMBOL(inet_sock_destruct);
@@ -1518,14 +1519,15 @@ static const struct net_protocol igmp_protocol = {
 #endif
 
 static const struct net_protocol tcp_protocol = {
-	.handler =	tcp_v4_rcv,
-	.err_handler =	tcp_v4_err,
-	.gso_send_check = tcp_v4_gso_send_check,
-	.gso_segment =	tcp_tso_segment,
-	.gro_receive =	tcp4_gro_receive,
-	.gro_complete =	tcp4_gro_complete,
-	.no_policy =	1,
-	.netns_ok =	1,
+	.early_demux	=	tcp_v4_early_demux,
+	.handler	=	tcp_v4_rcv,
+	.err_handler	=	tcp_v4_err,
+	.gso_send_check	=	tcp_v4_gso_send_check,
+	.gso_segment	=	tcp_tso_segment,
+	.gro_receive	=	tcp4_gro_receive,
+	.gro_complete	=	tcp4_gro_complete,
+	.no_policy	=	1,
+	.netns_ok	=	1,
 };
 
 static const struct net_protocol udp_protocol = {
diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c
index c4fe1d27113..93b092c9a39 100644
--- a/net/ipv4/ip_input.c
+++ b/net/ipv4/ip_input.c
@@ -323,19 +323,32 @@ static int ip_rcv_finish(struct sk_buff *skb)
 	 *	how the packet travels inside Linux networking.
 	 */
 	if (skb_dst(skb) == NULL) {
-		int err = ip_route_input_noref(skb, iph->daddr, iph->saddr,
-					       iph->tos, skb->dev);
-		if (unlikely(err)) {
-			if (err == -EHOSTUNREACH)
-				IP_INC_STATS_BH(dev_net(skb->dev),
-						IPSTATS_MIB_INADDRERRORS);
-			else if (err == -ENETUNREACH)
-				IP_INC_STATS_BH(dev_net(skb->dev),
-						IPSTATS_MIB_INNOROUTES);
-			else if (err == -EXDEV)
-				NET_INC_STATS_BH(dev_net(skb->dev),
-						 LINUX_MIB_IPRPFILTER);
-			goto drop;
+		const struct net_protocol *ipprot;
+		int protocol = iph->protocol;
+		int err;
+
+		rcu_read_lock();
+		ipprot = rcu_dereference(inet_protos[protocol]);
+		err = -ENOENT;
+		if (ipprot && ipprot->early_demux)
+			err = ipprot->early_demux(skb);
+		rcu_read_unlock();
+
+		if (err) {
+			err = ip_route_input_noref(skb, iph->daddr, iph->saddr,
+						   iph->tos, skb->dev);
+			if (unlikely(err)) {
+				if (err == -EHOSTUNREACH)
+					IP_INC_STATS_BH(dev_net(skb->dev),
+							IPSTATS_MIB_INADDRERRORS);
+				else if (err == -ENETUNREACH)
+					IP_INC_STATS_BH(dev_net(skb->dev),
+							IPSTATS_MIB_INNOROUTES);
+				else if (err == -EXDEV)
+					NET_INC_STATS_BH(dev_net(skb->dev),
+							 LINUX_MIB_IPRPFILTER);
+				goto drop;
+			}
 		}
 	}
 
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index b224eb8bce8..8416f8a68e6 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -5518,6 +5518,18 @@ int tcp_rcv_established(struct sock *sk, struct sk_buff *skb,
 	struct tcp_sock *tp = tcp_sk(sk);
 	int res;
 
+	if (sk->sk_rx_dst) {
+		struct dst_entry *dst = sk->sk_rx_dst;
+		if (unlikely(dst->obsolete)) {
+			if (dst->ops->check(dst, 0) == NULL) {
+				dst_release(dst);
+				sk->sk_rx_dst = NULL;
+			}
+		}
+	}
+	if (unlikely(sk->sk_rx_dst == NULL))
+		sk->sk_rx_dst = dst_clone(skb_dst(skb));
+
 	/*
 	 *	Header prediction.
 	 *	The code loosely follows the one in the famous
@@ -5729,8 +5741,10 @@ void tcp_finish_connect(struct sock *sk, struct sk_buff *skb)
 
 	tcp_set_state(sk, TCP_ESTABLISHED);
 
-	if (skb != NULL)
+	if (skb != NULL) {
+		sk->sk_rx_dst = dst_clone(skb_dst(skb));
 		security_inet_conn_established(sk, skb);
+	}
 
 	/* Make sure socket is routed, for correct metrics.  */
 	icsk->icsk_af_ops->rebuild_header(sk);
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index fda2ca17135..13857df1dae 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1671,6 +1671,52 @@ csum_err:
 }
 EXPORT_SYMBOL(tcp_v4_do_rcv);
 
+int tcp_v4_early_demux(struct sk_buff *skb)
+{
+	struct net *net = dev_net(skb->dev);
+	const struct iphdr *iph;
+	const struct tcphdr *th;
+	struct sock *sk;
+	int err;
+
+	err = -ENOENT;
+	if (skb->pkt_type != PACKET_HOST)
+		goto out_err;
+
+	if (!pskb_may_pull(skb, ip_hdrlen(skb) + sizeof(struct tcphdr)))
+		goto out_err;
+
+	iph = ip_hdr(skb);
+	th = (struct tcphdr *) ((char *)iph + ip_hdrlen(skb));
+
+	if (th->doff < sizeof(struct tcphdr) / 4)
+		goto out_err;
+
+	if (!pskb_may_pull(skb, ip_hdrlen(skb) + th->doff * 4))
+		goto out_err;
+
+	sk = __inet_lookup_established(net, &tcp_hashinfo,
+				       iph->saddr, th->source,
+				       iph->daddr, th->dest,
+				       skb->dev->ifindex);
+	if (sk) {
+		skb->sk = sk;
+		skb->destructor = sock_edemux;
+		if (sk->sk_state != TCP_TIME_WAIT) {
+			struct dst_entry *dst = sk->sk_rx_dst;
+			if (dst)
+				dst = dst_check(dst, 0);
+			if (dst) {
+				skb_dst_set_noref(skb, dst);
+				err = 0;
+			}
+		}
+	}
+
+out_err:
+	return err;
+}
+
 /*
  *	From tcp_input.c
  */
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index cb015317c9f..72b7c63b1a3 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -445,6 +445,8 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req,
 		struct tcp_sock *oldtp = tcp_sk(sk);
 		struct tcp_cookie_values *oldcvp = oldtp->cookie_values;
 
+		newsk->sk_rx_dst = dst_clone(skb_dst(skb));
+
 		/* TCP Cookie Transactions require space for the cookie pair,
 		 * as it differs for each connection.  There is no need to
 		 * copy any s_data_payload stored at the original socket.
-- 
cgit v1.2.3-70-g09d2


From 81166dd6fa8eb780b2132d32fbc77eb6ac04e44e Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Tue, 10 Jul 2012 03:14:24 -0700
Subject: tcp: Move timestamps from inetpeer to metrics cache.

With help from Lin Ming.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/inetpeer.h   |   4 +-
 include/net/tcp.h        |   5 +-
 net/ipv4/inetpeer.c      |   1 -
 net/ipv4/route.c         |   8 +--
 net/ipv4/tcp_ipv4.c      |  30 ++---------
 net/ipv4/tcp_metrics.c   | 136 +++++++++++++++++++++++++++++++++++++++++++++--
 net/ipv4/tcp_minisocks.c |  46 ----------------
 net/ipv6/route.c         |  13 +----
 net/ipv6/tcp_ipv6.c      |  33 ++----------
 9 files changed, 149 insertions(+), 127 deletions(-)

(limited to 'net/ipv4/tcp_minisocks.c')

diff --git a/include/net/inetpeer.h b/include/net/inetpeer.h
index c27c8f10ebd..1119f6f6cdb 100644
--- a/include/net/inetpeer.h
+++ b/include/net/inetpeer.h
@@ -46,15 +46,13 @@ struct inet_peer {
 	};
 	/*
 	 * Once inet_peer is queued for deletion (refcnt == -1), following fields
-	 * are not available: rid, ip_id_count, tcp_ts, tcp_ts_stamp
+	 * are not available: rid, ip_id_count
 	 * We can share memory with rcu_head to help keep inet_peer small.
 	 */
 	union {
 		struct {
 			atomic_t			rid;		/* Frag reception counter */
 			atomic_t			ip_id_count;	/* IP ID for the next packet */
-			__u32				tcp_ts;
-			__u32				tcp_ts_stamp;
 		};
 		struct rcu_head         rcu;
 		struct inet_peer	*gc_next;
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 0900d63d162..3618fefae04 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -390,7 +390,10 @@ extern void tcp_clear_retrans(struct tcp_sock *tp);
 extern void tcp_update_metrics(struct sock *sk);
 extern void tcp_init_metrics(struct sock *sk);
 extern void tcp_metrics_init(void);
-extern bool tcp_peer_is_proven(struct request_sock *req, struct dst_entry *dst);
+extern bool tcp_peer_is_proven(struct request_sock *req, struct dst_entry *dst, bool paws_check);
+extern bool tcp_remember_stamp(struct sock *sk);
+extern bool tcp_tw_remember_stamp(struct inet_timewait_sock *tw);
+extern void tcp_fetch_timewait_stamp(struct sock *sk, struct dst_entry *dst);
 extern void tcp_disable_fack(struct tcp_sock *tp);
 extern void tcp_close(struct sock *sk, long timeout);
 extern void tcp_init_sock(struct sock *sk);
diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c
index da90a8cab61..f457bcb4135 100644
--- a/net/ipv4/inetpeer.c
+++ b/net/ipv4/inetpeer.c
@@ -508,7 +508,6 @@ relookup:
 				(daddr->family == AF_INET) ?
 					secure_ip_id(daddr->addr.a4) :
 					secure_ipv6_id(daddr->addr.a6));
-		p->tcp_ts_stamp = 0;
 		p->metrics[RTAX_LOCK-1] = INETPEER_METRICS_NEW;
 		p->rate_tokens = 0;
 		p->rate_last = 0;
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index d02c91177d3..78d81543766 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -2846,7 +2846,7 @@ static int rt_fill_info(struct net *net,
 	struct rtmsg *r;
 	struct nlmsghdr *nlh;
 	unsigned long expires = 0;
-	u32 id = 0, ts = 0, tsage = 0, error;
+	u32 id = 0, error;
 
 	nlh = nlmsg_put(skb, pid, seq, event, sizeof(*r), flags);
 	if (nlh == NULL)
@@ -2903,10 +2903,6 @@ static int rt_fill_info(struct net *net,
 		const struct inet_peer *peer = rt_peer_ptr(rt);
 		inet_peer_refcheck(peer);
 		id = atomic_read(&peer->ip_id_count) & 0xffff;
-		if (peer->tcp_ts_stamp) {
-			ts = peer->tcp_ts;
-			tsage = get_seconds() - peer->tcp_ts_stamp;
-		}
 		expires = ACCESS_ONCE(peer->pmtu_expires);
 		if (expires) {
 			if (time_before(jiffies, expires))
@@ -2942,7 +2938,7 @@ static int rt_fill_info(struct net *net,
 				goto nla_put_failure;
 	}
 
-	if (rtnl_put_cacheinfo(skb, &rt->dst, id, ts, tsage,
+	if (rtnl_put_cacheinfo(skb, &rt->dst, id, 0, 0,
 			       expires, error) < 0)
 		goto nla_put_failure;
 
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index e9312a8f33a..d406bf7f37d 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -209,22 +209,8 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 	}
 
 	if (tcp_death_row.sysctl_tw_recycle &&
-	    !tp->rx_opt.ts_recent_stamp && fl4->daddr == daddr) {
-		struct inet_peer *peer = rt_get_peer(rt, fl4->daddr);
-		/*
-		 * VJ's idea. We save last timestamp seen from
-		 * the destination in peer table, when entering state
-		 * TIME-WAIT * and initialize rx_opt.ts_recent from it,
-		 * when trying new connection.
-		 */
-		if (peer) {
-			inet_peer_refcheck(peer);
-			if ((u32)get_seconds() - peer->tcp_ts_stamp <= TCP_PAWS_MSL) {
-				tp->rx_opt.ts_recent_stamp = peer->tcp_ts_stamp;
-				tp->rx_opt.ts_recent = peer->tcp_ts;
-			}
-		}
-	}
+	    !tp->rx_opt.ts_recent_stamp && fl4->daddr == daddr)
+		tcp_fetch_timewait_stamp(sk, &rt->dst);
 
 	inet->inet_dport = usin->sin_port;
 	inet->inet_daddr = daddr;
@@ -1375,7 +1361,6 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
 		isn = cookie_v4_init_sequence(sk, skb, &req->mss);
 		req->cookie_ts = tmp_opt.tstamp_ok;
 	} else if (!isn) {
-		struct inet_peer *peer = NULL;
 		struct flowi4 fl4;
 
 		/* VJ's idea. We save last timestamp seen
@@ -1390,12 +1375,8 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
 		if (tmp_opt.saw_tstamp &&
 		    tcp_death_row.sysctl_tw_recycle &&
 		    (dst = inet_csk_route_req(sk, &fl4, req, want_cookie)) != NULL &&
-		    fl4.daddr == saddr &&
-		    (peer = rt_get_peer((struct rtable *)dst, fl4.daddr)) != NULL) {
-			inet_peer_refcheck(peer);
-			if ((u32)get_seconds() - peer->tcp_ts_stamp < TCP_PAWS_MSL &&
-			    (s32)(peer->tcp_ts - req->ts_recent) >
-							TCP_PAWS_WINDOW) {
+		    fl4.daddr == saddr) {
+			if (!tcp_peer_is_proven(req, dst, true)) {
 				NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_PAWSPASSIVEREJECTED);
 				goto drop_and_release;
 			}
@@ -1404,8 +1385,7 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
 		else if (!sysctl_tcp_syncookies &&
 			 (sysctl_max_syn_backlog - inet_csk_reqsk_queue_len(sk) <
 			  (sysctl_max_syn_backlog >> 2)) &&
-			 (!peer || !peer->tcp_ts_stamp) &&
-			 !tcp_peer_is_proven(req, dst)) {
+			 !tcp_peer_is_proven(req, dst, false)) {
 			/* Without syncookies last quarter of
 			 * backlog is filled with destinations,
 			 * proven to be alive.
diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c
index 56223bab251..1fd83d3118f 100644
--- a/net/ipv4/tcp_metrics.c
+++ b/net/ipv4/tcp_metrics.c
@@ -34,6 +34,8 @@ struct tcp_metrics_block {
 	struct tcp_metrics_block __rcu	*tcpm_next;
 	struct inetpeer_addr		tcpm_addr;
 	unsigned long			tcpm_stamp;
+	u32				tcpm_ts;
+	u32				tcpm_ts_stamp;
 	u32				tcpm_lock;
 	u32				tcpm_vals[TCP_METRIC_MAX];
 };
@@ -114,6 +116,8 @@ static void tcpm_suck_dst(struct tcp_metrics_block *tm, struct dst_entry *dst)
 	tm->tcpm_vals[TCP_METRIC_SSTHRESH] = dst_metric_raw(dst, RTAX_SSTHRESH);
 	tm->tcpm_vals[TCP_METRIC_CWND] = dst_metric_raw(dst, RTAX_CWND);
 	tm->tcpm_vals[TCP_METRIC_REORDERING] = dst_metric_raw(dst, RTAX_REORDERING);
+	tm->tcpm_ts = 0;
+	tm->tcpm_ts_stamp = 0;
 }
 
 static struct tcp_metrics_block *tcpm_new(struct dst_entry *dst,
@@ -230,6 +234,45 @@ static struct tcp_metrics_block *__tcp_get_metrics_req(struct request_sock *req,
 	return tm;
 }
 
+static struct tcp_metrics_block *__tcp_get_metrics_tw(struct inet_timewait_sock *tw)
+{
+	struct inet6_timewait_sock *tw6;
+	struct tcp_metrics_block *tm;
+	struct inetpeer_addr addr;
+	unsigned int hash;
+	struct net *net;
+
+	addr.family = tw->tw_family;
+	switch (addr.family) {
+	case AF_INET:
+		addr.addr.a4 = tw->tw_daddr;
+		hash = (__force unsigned int) addr.addr.a4;
+		break;
+	case AF_INET6:
+		tw6 = inet6_twsk((struct sock *)tw);
+		*(struct in6_addr *)addr.addr.a6 = tw6->tw_v6_daddr;
+		hash = ((__force unsigned int) addr.addr.a6[0] ^
+			(__force unsigned int) addr.addr.a6[1] ^
+			(__force unsigned int) addr.addr.a6[2] ^
+			(__force unsigned int) addr.addr.a6[3]);
+		break;
+	default:
+		return NULL;
+	}
+
+	hash ^= (hash >> 24) ^ (hash >> 16) ^ (hash >> 8);
+
+	net = twsk_net(tw);
+	hash &= net->ipv4.tcp_metrics_hash_mask;
+
+	for (tm = rcu_dereference(net->ipv4.tcp_metrics_hash[hash].chain); tm;
+	     tm = rcu_dereference(tm->tcpm_next)) {
+		if (addr_same(&tm->tcpm_addr, &addr))
+			break;
+	}
+	return tm;
+}
+
 static struct tcp_metrics_block *tcp_get_metrics(struct sock *sk,
 						 struct dst_entry *dst,
 						 bool create)
@@ -496,7 +539,7 @@ reset:
 	tp->snd_cwnd_stamp = tcp_time_stamp;
 }
 
-bool tcp_peer_is_proven(struct request_sock *req, struct dst_entry *dst)
+bool tcp_peer_is_proven(struct request_sock *req, struct dst_entry *dst, bool paws_check)
 {
 	struct tcp_metrics_block *tm;
 	bool ret;
@@ -506,16 +549,99 @@ bool tcp_peer_is_proven(struct request_sock *req, struct dst_entry *dst)
 
 	rcu_read_lock();
 	tm = __tcp_get_metrics_req(req, dst);
-	if (tm && tcp_metric_get(tm, TCP_METRIC_RTT))
-		ret = true;
-	else
-		ret = false;
+	if (paws_check) {
+		if (tm &&
+		    (u32)get_seconds() - tm->tcpm_ts_stamp < TCP_PAWS_MSL &&
+		    (s32)(tm->tcpm_ts - req->ts_recent) > TCP_PAWS_WINDOW)
+			ret = false;
+		else
+			ret = true;
+	} else {
+		if (tm && tcp_metric_get(tm, TCP_METRIC_RTT) && tm->tcpm_ts_stamp)
+			ret = true;
+		else
+			ret = false;
+	}
 	rcu_read_unlock();
 
 	return ret;
 }
 EXPORT_SYMBOL_GPL(tcp_peer_is_proven);
 
+void tcp_fetch_timewait_stamp(struct sock *sk, struct dst_entry *dst)
+{
+	struct tcp_metrics_block *tm;
+
+	rcu_read_lock();
+	tm = tcp_get_metrics(sk, dst, true);
+	if (tm) {
+		struct tcp_sock *tp = tcp_sk(sk);
+
+		if ((u32)get_seconds() - tm->tcpm_ts_stamp <= TCP_PAWS_MSL) {
+			tp->rx_opt.ts_recent_stamp = tm->tcpm_ts_stamp;
+			tp->rx_opt.ts_recent = tm->tcpm_ts;
+		}
+	}
+	rcu_read_unlock();
+}
+EXPORT_SYMBOL_GPL(tcp_fetch_timewait_stamp);
+
+/* VJ's idea. Save last timestamp seen from this destination and hold
+ * it at least for normal timewait interval to use for duplicate
+ * segment detection in subsequent connections, before they enter
+ * synchronized state.
+ */
+bool tcp_remember_stamp(struct sock *sk)
+{
+	struct dst_entry *dst = __sk_dst_get(sk);
+	bool ret = false;
+
+	if (dst) {
+		struct tcp_metrics_block *tm;
+
+		rcu_read_lock();
+		tm = tcp_get_metrics(sk, dst, true);
+		if (tm) {
+			struct tcp_sock *tp = tcp_sk(sk);
+
+			if ((s32)(tm->tcpm_ts - tp->rx_opt.ts_recent) <= 0 ||
+			    ((u32)get_seconds() - tm->tcpm_ts_stamp > TCP_PAWS_MSL &&
+			     tm->tcpm_ts_stamp <= (u32)tp->rx_opt.ts_recent_stamp)) {
+				tm->tcpm_ts_stamp = (u32)tp->rx_opt.ts_recent_stamp;
+				tm->tcpm_ts = tp->rx_opt.ts_recent;
+			}
+			ret = true;
+		}
+		rcu_read_unlock();
+	}
+	return ret;
+}
+
+bool tcp_tw_remember_stamp(struct inet_timewait_sock *tw)
+{
+	struct tcp_metrics_block *tm;
+	bool ret = false;
+
+	rcu_read_lock();
+	tm = __tcp_get_metrics_tw(tw);
+	if (tw) {
+		const struct tcp_timewait_sock *tcptw;
+		struct sock *sk = (struct sock *) tw;
+
+		tcptw = tcp_twsk(sk);
+		if ((s32)(tm->tcpm_ts - tcptw->tw_ts_recent) <= 0 ||
+		    ((u32)get_seconds() - tm->tcpm_ts_stamp > TCP_PAWS_MSL &&
+		     tm->tcpm_ts_stamp <= (u32)tcptw->tw_ts_recent_stamp)) {
+			tm->tcpm_ts_stamp = (u32)tcptw->tw_ts_recent_stamp;
+			tm->tcpm_ts	   = tcptw->tw_ts_recent;
+		}
+		ret = true;
+	}
+	rcu_read_unlock();
+
+	return ret;
+}
+
 static unsigned long tcpmhash_entries;
 static int __init set_tcpmhash_entries(char *str)
 {
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 72b7c63b1a3..a51aa534dab 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -49,52 +49,6 @@ struct inet_timewait_death_row tcp_death_row = {
 };
 EXPORT_SYMBOL_GPL(tcp_death_row);
 
-/* VJ's idea. Save last timestamp seen from this destination
- * and hold it at least for normal timewait interval to use for duplicate
- * segment detection in subsequent connections, before they enter synchronized
- * state.
- */
-
-static bool tcp_remember_stamp(struct sock *sk)
-{
-	const struct inet_connection_sock *icsk = inet_csk(sk);
-	struct tcp_sock *tp = tcp_sk(sk);
-	struct inet_peer *peer;
-
-	peer = icsk->icsk_af_ops->get_peer(sk);
-	if (peer) {
-		if ((s32)(peer->tcp_ts - tp->rx_opt.ts_recent) <= 0 ||
-		    ((u32)get_seconds() - peer->tcp_ts_stamp > TCP_PAWS_MSL &&
-		     peer->tcp_ts_stamp <= (u32)tp->rx_opt.ts_recent_stamp)) {
-			peer->tcp_ts_stamp = (u32)tp->rx_opt.ts_recent_stamp;
-			peer->tcp_ts = tp->rx_opt.ts_recent;
-		}
-		return true;
-	}
-
-	return false;
-}
-
-static bool tcp_tw_remember_stamp(struct inet_timewait_sock *tw)
-{
-	const struct tcp_timewait_sock *tcptw;
-	struct sock *sk = (struct sock *) tw;
-	struct inet_peer *peer;
-
-	tcptw = tcp_twsk(sk);
-	peer = tcptw->tw_peer;
-	if (peer) {
-		if ((s32)(peer->tcp_ts - tcptw->tw_ts_recent) <= 0 ||
-		    ((u32)get_seconds() - peer->tcp_ts_stamp > TCP_PAWS_MSL &&
-		     peer->tcp_ts_stamp <= (u32)tcptw->tw_ts_recent_stamp)) {
-			peer->tcp_ts_stamp = (u32)tcptw->tw_ts_recent_stamp;
-			peer->tcp_ts	   = tcptw->tw_ts_recent;
-		}
-		return true;
-	}
-	return false;
-}
-
 static bool tcp_in_window(u32 seq, u32 end_seq, u32 s_win, u32 e_win)
 {
 	if (seq == s_win)
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 6cc6c881f54..0c068475378 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -2348,13 +2348,11 @@ static int rt6_fill_node(struct net *net,
 			 int iif, int type, u32 pid, u32 seq,
 			 int prefix, int nowait, unsigned int flags)
 {
-	const struct inet_peer *peer;
 	struct rtmsg *rtm;
 	struct nlmsghdr *nlh;
 	long expires;
 	u32 table;
 	struct neighbour *n;
-	u32 ts, tsage;
 
 	if (prefix) {	/* user wants prefix routes only */
 		if (!(rt->rt6i_flags & RTF_PREFIX_RT)) {
@@ -2473,16 +2471,7 @@ static int rt6_fill_node(struct net *net,
 	else
 		expires = INT_MAX;
 
-	peer = NULL;
-	if (rt6_has_peer(rt))
-		peer = rt6_peer_ptr(rt);
-	ts = tsage = 0;
-	if (peer && peer->tcp_ts_stamp) {
-		ts = peer->tcp_ts;
-		tsage = get_seconds() - peer->tcp_ts_stamp;
-	}
-
-	if (rtnl_put_cacheinfo(skb, &rt->dst, 0, ts, tsage,
+	if (rtnl_put_cacheinfo(skb, &rt->dst, 0, 0, 0,
 			       expires, rt->dst.error) < 0)
 		goto nla_put_failure;
 
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 75d179555c2..9e96b5f21d2 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -277,22 +277,8 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 	rt = (struct rt6_info *) dst;
 	if (tcp_death_row.sysctl_tw_recycle &&
 	    !tp->rx_opt.ts_recent_stamp &&
-	    ipv6_addr_equal(&rt->rt6i_dst.addr, &np->daddr)) {
-		struct inet_peer *peer = rt6_get_peer(rt);
-		/*
-		 * VJ's idea. We save last timestamp seen from
-		 * the destination in peer table, when entering state
-		 * TIME-WAIT * and initialize rx_opt.ts_recent from it,
-		 * when trying new connection.
-		 */
-		if (peer) {
-			inet_peer_refcheck(peer);
-			if ((u32)get_seconds() - peer->tcp_ts_stamp <= TCP_PAWS_MSL) {
-				tp->rx_opt.ts_recent_stamp = peer->tcp_ts_stamp;
-				tp->rx_opt.ts_recent = peer->tcp_ts;
-			}
-		}
-	}
+	    ipv6_addr_equal(&rt->rt6i_dst.addr, &np->daddr))
+		tcp_fetch_timewait_stamp(sk, dst);
 
 	icsk->icsk_ext_hdr_len = 0;
 	if (np->opt)
@@ -1134,8 +1120,6 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
 		treq->iif = inet6_iif(skb);
 
 	if (!isn) {
-		struct inet_peer *peer = NULL;
-
 		if (ipv6_opt_accepted(sk, skb) ||
 		    np->rxopt.bits.rxinfo || np->rxopt.bits.rxoinfo ||
 		    np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim) {
@@ -1160,14 +1144,8 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
 		 */
 		if (tmp_opt.saw_tstamp &&
 		    tcp_death_row.sysctl_tw_recycle &&
-		    (dst = inet6_csk_route_req(sk, &fl6, req)) != NULL &&
-		    (peer = rt6_get_peer((struct rt6_info *)dst)) != NULL &&
-		    ipv6_addr_equal((struct in6_addr *)peer->daddr.addr.a6,
-				    &treq->rmt_addr)) {
-			inet_peer_refcheck(peer);
-			if ((u32)get_seconds() - peer->tcp_ts_stamp < TCP_PAWS_MSL &&
-			    (s32)(peer->tcp_ts - req->ts_recent) >
-							TCP_PAWS_WINDOW) {
+		    (dst = inet6_csk_route_req(sk, &fl6, req)) != NULL) {
+			if (!tcp_peer_is_proven(req, dst, true)) {
 				NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_PAWSPASSIVEREJECTED);
 				goto drop_and_release;
 			}
@@ -1176,8 +1154,7 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
 		else if (!sysctl_tcp_syncookies &&
 			 (sysctl_max_syn_backlog - inet_csk_reqsk_queue_len(sk) <
 			  (sysctl_max_syn_backlog >> 2)) &&
-			 (!peer || !peer->tcp_ts_stamp) &&
-			 !tcp_peer_is_proven(req, dst)) {
+			 !tcp_peer_is_proven(req, dst, false)) {
 			/* Without syncookies last quarter of
 			 * backlog is filled with destinations,
 			 * proven to be alive.
-- 
cgit v1.2.3-70-g09d2


From b6242b9b45e84ef71c59002cd128c3197938cb2f Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Tue, 10 Jul 2012 03:27:56 -0700
Subject: tcp: Remove tw->tw_peer

No longer used.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/tcp.h      |  1 -
 net/ipv4/tcp_minisocks.c | 16 ++--------------
 2 files changed, 2 insertions(+), 15 deletions(-)

(limited to 'net/ipv4/tcp_minisocks.c')

diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index 7d3bcedc062..2de9cf46f9f 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -506,7 +506,6 @@ struct tcp_timewait_sock {
 	u32			  tw_rcv_wnd;
 	u32			  tw_ts_recent;
 	long			  tw_ts_recent_stamp;
-	struct inet_peer	  *tw_peer;
 #ifdef CONFIG_TCP_MD5SIG
 	struct tcp_md5sig_key	  *tw_md5_key;
 #endif
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index a51aa534dab..65608863fde 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -267,12 +267,9 @@ void tcp_time_wait(struct sock *sk, int state, int timeo)
 	const struct inet_connection_sock *icsk = inet_csk(sk);
 	const struct tcp_sock *tp = tcp_sk(sk);
 	bool recycle_ok = false;
-	bool recycle_on = false;
 
-	if (tcp_death_row.sysctl_tw_recycle && tp->rx_opt.ts_recent_stamp) {
+	if (tcp_death_row.sysctl_tw_recycle && tp->rx_opt.ts_recent_stamp)
 		recycle_ok = tcp_remember_stamp(sk);
-		recycle_on = true;
-	}
 
 	if (tcp_death_row.tw_count < tcp_death_row.sysctl_max_tw_buckets)
 		tw = inet_twsk_alloc(sk, state);
@@ -281,7 +278,6 @@ void tcp_time_wait(struct sock *sk, int state, int timeo)
 		struct tcp_timewait_sock *tcptw = tcp_twsk((struct sock *)tw);
 		const int rto = (icsk->icsk_rto << 2) - (icsk->icsk_rto >> 1);
 		struct inet_sock *inet = inet_sk(sk);
-		struct inet_peer *peer = NULL;
 
 		tw->tw_transparent	= inet->transparent;
 		tw->tw_rcv_wscale	= tp->rx_opt.rcv_wscale;
@@ -305,12 +301,6 @@ void tcp_time_wait(struct sock *sk, int state, int timeo)
 		}
 #endif
 
-		if (recycle_on)
-			peer = icsk->icsk_af_ops->get_peer(sk);
-		tcptw->tw_peer = peer;
-		if (peer)
-			atomic_inc(&peer->refcnt);
-
 #ifdef CONFIG_TCP_MD5SIG
 		/*
 		 * The timewait bucket does not have the key DB from the
@@ -362,11 +352,9 @@ void tcp_time_wait(struct sock *sk, int state, int timeo)
 
 void tcp_twsk_destructor(struct sock *sk)
 {
+#ifdef CONFIG_TCP_MD5SIG
 	struct tcp_timewait_sock *twsk = tcp_twsk(sk);
 
-	if (twsk->tw_peer)
-		inet_putpeer(twsk->tw_peer);
-#ifdef CONFIG_TCP_MD5SIG
 	if (twsk->tw_md5_key) {
 		tcp_free_md5sig_pool();
 		kfree_rcu(twsk->tw_md5_key, rcu);
-- 
cgit v1.2.3-70-g09d2


From 46d3ceabd8d98ed0ad10f20c595ca784e34786c5 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <eric.dumazet@gmail.com>
Date: Wed, 11 Jul 2012 05:50:31 +0000
Subject: tcp: TCP Small Queues

This introduce TSQ (TCP Small Queues)

TSQ goal is to reduce number of TCP packets in xmit queues (qdisc &
device queues), to reduce RTT and cwnd bias, part of the bufferbloat
problem.

sk->sk_wmem_alloc not allowed to grow above a given limit,
allowing no more than ~128KB [1] per tcp socket in qdisc/dev layers at a
given time.

TSO packets are sized/capped to half the limit, so that we have two
TSO packets in flight, allowing better bandwidth use.

As a side effect, setting the limit to 40000 automatically reduces the
standard gso max limit (65536) to 40000/2 : It can help to reduce
latencies of high prio packets, having smaller TSO packets.

This means we divert sock_wfree() to a tcp_wfree() handler, to
queue/send following frames when skb_orphan() [2] is called for the
already queued skbs.

Results on my dev machines (tg3/ixgbe nics) are really impressive,
using standard pfifo_fast, and with or without TSO/GSO.

Without reduction of nominal bandwidth, we have reduction of buffering
per bulk sender :
< 1ms on Gbit (instead of 50ms with TSO)
< 8ms on 100Mbit (instead of 132 ms)

I no longer have 4 MBytes backlogged in qdisc by a single netperf
session, and both side socket autotuning no longer use 4 Mbytes.

As skb destructor cannot restart xmit itself ( as qdisc lock might be
taken at this point ), we delegate the work to a tasklet. We use one
tasklest per cpu for performance reasons.

If tasklet finds a socket owned by the user, it sets TSQ_OWNED flag.
This flag is tested in a new protocol method called from release_sock(),
to eventually send new segments.

[1] New /proc/sys/net/ipv4/tcp_limit_output_bytes tunable
[2] skb_orphan() is usually called at TX completion time,
  but some drivers call it in their start_xmit() handler.
  These drivers should at least use BQL, or else a single TCP
  session can still fill the whole NIC TX ring, since TSQ will
  have no effect.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Dave Taht <dave.taht@bufferbloat.net>
Cc: Tom Herbert <therbert@google.com>
Cc: Matt Mathis <mattmathis@google.com>
Cc: Yuchung Cheng <ycheng@google.com>
Cc: Nandita Dukkipati <nanditad@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/networking/ip-sysctl.txt |  14 +++
 include/linux/tcp.h                    |   9 ++
 include/net/sock.h                     |   2 +
 include/net/tcp.h                      |   4 +
 net/core/sock.c                        |   4 +
 net/ipv4/sysctl_net_ipv4.c             |   7 ++
 net/ipv4/tcp.c                         |   6 ++
 net/ipv4/tcp_ipv4.c                    |   1 +
 net/ipv4/tcp_minisocks.c               |   1 +
 net/ipv4/tcp_output.c                  | 154 ++++++++++++++++++++++++++++++++-
 net/ipv6/tcp_ipv6.c                    |   1 +
 11 files changed, 202 insertions(+), 1 deletion(-)

(limited to 'net/ipv4/tcp_minisocks.c')

diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index 47b6c79e9b0..e20c17a7d34 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -551,6 +551,20 @@ tcp_thin_dupack - BOOLEAN
 	Documentation/networking/tcp-thin.txt
 	Default: 0
 
+tcp_limit_output_bytes - INTEGER
+	Controls TCP Small Queue limit per tcp socket.
+	TCP bulk sender tends to increase packets in flight until it
+	gets losses notifications. With SNDBUF autotuning, this can
+	result in a large amount of packets queued in qdisc/device
+	on the local machine, hurting latency of other flows, for
+	typical pfifo_fast qdiscs.
+	tcp_limit_output_bytes limits the number of bytes on qdisc
+	or device to reduce artificial RTT/cwnd and reduce bufferbloat.
+	Note: For GSO/TSO enabled flows, we try to have at least two
+	packets in flight. Reducing tcp_limit_output_bytes might also
+	reduce the size of individual GSO packet (64KB being the max)
+	Default: 131072
+
 UDP variables:
 
 udp_mem - vector of 3 INTEGERs: min, pressure, max
diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index 2de9cf46f9f..1888169e07c 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -339,6 +339,9 @@ struct tcp_sock {
 	u32	rcv_tstamp;	/* timestamp of last received ACK (for keepalives) */
 	u32	lsndtime;	/* timestamp of last sent data packet (for restart window) */
 
+	struct list_head tsq_node; /* anchor in tsq_tasklet.head list */
+	unsigned long	tsq_flags;
+
 	/* Data for direct copy to user */
 	struct {
 		struct sk_buff_head	prequeue;
@@ -494,6 +497,12 @@ struct tcp_sock {
 	struct tcp_cookie_values  *cookie_values;
 };
 
+enum tsq_flags {
+	TSQ_THROTTLED,
+	TSQ_QUEUED,
+	TSQ_OWNED, /* tcp_tasklet_func() found socket was locked */
+};
+
 static inline struct tcp_sock *tcp_sk(const struct sock *sk)
 {
 	return (struct tcp_sock *)sk;
diff --git a/include/net/sock.h b/include/net/sock.h
index dcb54a0793e..88de092df50 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -858,6 +858,8 @@ struct proto {
 	int			(*backlog_rcv) (struct sock *sk,
 						struct sk_buff *skb);
 
+	void		(*release_cb)(struct sock *sk);
+
 	/* Keeping track of sk's, looking them up, and port selection methods. */
 	void			(*hash)(struct sock *sk);
 	void			(*unhash)(struct sock *sk);
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 3618fefae04..439984b9af4 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -253,6 +253,7 @@ extern int sysctl_tcp_cookie_size;
 extern int sysctl_tcp_thin_linear_timeouts;
 extern int sysctl_tcp_thin_dupack;
 extern int sysctl_tcp_early_retrans;
+extern int sysctl_tcp_limit_output_bytes;
 
 extern atomic_long_t tcp_memory_allocated;
 extern struct percpu_counter tcp_sockets_allocated;
@@ -321,6 +322,8 @@ extern struct proto tcp_prot;
 
 extern void tcp_init_mem(struct net *net);
 
+extern void tcp_tasklet_init(void);
+
 extern void tcp_v4_err(struct sk_buff *skb, u32);
 
 extern void tcp_shutdown (struct sock *sk, int how);
@@ -334,6 +337,7 @@ extern int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 		       size_t size);
 extern int tcp_sendpage(struct sock *sk, struct page *page, int offset,
 			size_t size, int flags);
+extern void tcp_release_cb(struct sock *sk);
 extern int tcp_ioctl(struct sock *sk, int cmd, unsigned long arg);
 extern int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb,
 				 const struct tcphdr *th, unsigned int len);
diff --git a/net/core/sock.c b/net/core/sock.c
index 929bdcc2383..24039ac1242 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -2159,6 +2159,10 @@ void release_sock(struct sock *sk)
 	spin_lock_bh(&sk->sk_lock.slock);
 	if (sk->sk_backlog.tail)
 		__release_sock(sk);
+
+	if (sk->sk_prot->release_cb)
+		sk->sk_prot->release_cb(sk);
+
 	sk->sk_lock.owned = 0;
 	if (waitqueue_active(&sk->sk_lock.wq))
 		wake_up(&sk->sk_lock.wq);
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 12aa0c5867c..70730f7aeaf 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -598,6 +598,13 @@ static struct ctl_table ipv4_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec
 	},
+	{
+		.procname	= "tcp_limit_output_bytes",
+		.data		= &sysctl_tcp_limit_output_bytes,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec
+	},
 #ifdef CONFIG_NET_DMA
 	{
 		.procname	= "tcp_dma_copybreak",
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index d902da96d15..4252cd8f39f 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -376,6 +376,7 @@ void tcp_init_sock(struct sock *sk)
 	skb_queue_head_init(&tp->out_of_order_queue);
 	tcp_init_xmit_timers(sk);
 	tcp_prequeue_init(tp);
+	INIT_LIST_HEAD(&tp->tsq_node);
 
 	icsk->icsk_rto = TCP_TIMEOUT_INIT;
 	tp->mdev = TCP_TIMEOUT_INIT;
@@ -796,6 +797,10 @@ static unsigned int tcp_xmit_size_goal(struct sock *sk, u32 mss_now,
 				  inet_csk(sk)->icsk_ext_hdr_len -
 				  tp->tcp_header_len);
 
+		/* TSQ : try to have two TSO segments in flight */
+		xmit_size_goal = min_t(u32, xmit_size_goal,
+				       sysctl_tcp_limit_output_bytes >> 1);
+
 		xmit_size_goal = tcp_bound_to_half_wnd(tp, xmit_size_goal);
 
 		/* We try hard to avoid divides here */
@@ -3574,4 +3579,5 @@ void __init tcp_init(void)
 	tcp_secret_primary = &tcp_secret_one;
 	tcp_secret_retiring = &tcp_secret_two;
 	tcp_secret_secondary = &tcp_secret_two;
+	tcp_tasklet_init();
 }
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index ddefd39ac0c..01545a3fc0f 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -2588,6 +2588,7 @@ struct proto tcp_prot = {
 	.sendmsg		= tcp_sendmsg,
 	.sendpage		= tcp_sendpage,
 	.backlog_rcv		= tcp_v4_do_rcv,
+	.release_cb		= tcp_release_cb,
 	.hash			= inet_hash,
 	.unhash			= inet_unhash,
 	.get_port		= inet_csk_get_port,
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 65608863fde..c66f2ede160 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -424,6 +424,7 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req,
 			treq->snt_isn + 1 + tcp_s_data_size(oldtp);
 
 		tcp_prequeue_init(newtp);
+		INIT_LIST_HEAD(&newtp->tsq_node);
 
 		tcp_init_wl(newtp, treq->rcv_isn);
 
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index c465d3e51e2..03854abfd9d 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -50,6 +50,9 @@ int sysctl_tcp_retrans_collapse __read_mostly = 1;
  */
 int sysctl_tcp_workaround_signed_windows __read_mostly = 0;
 
+/* Default TSQ limit of two TSO segments */
+int sysctl_tcp_limit_output_bytes __read_mostly = 131072;
+
 /* This limits the percentage of the congestion window which we
  * will allow a single TSO frame to consume.  Building TSO frames
  * which are too large can cause TCP streams to be bursty.
@@ -65,6 +68,8 @@ int sysctl_tcp_slow_start_after_idle __read_mostly = 1;
 int sysctl_tcp_cookie_size __read_mostly = 0; /* TCP_COOKIE_MAX */
 EXPORT_SYMBOL_GPL(sysctl_tcp_cookie_size);
 
+static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
+			   int push_one, gfp_t gfp);
 
 /* Account for new data that has been sent to the network. */
 static void tcp_event_new_data_sent(struct sock *sk, const struct sk_buff *skb)
@@ -783,6 +788,140 @@ static unsigned int tcp_established_options(struct sock *sk, struct sk_buff *skb
 	return size;
 }
 
+
+/* TCP SMALL QUEUES (TSQ)
+ *
+ * TSQ goal is to keep small amount of skbs per tcp flow in tx queues (qdisc+dev)
+ * to reduce RTT and bufferbloat.
+ * We do this using a special skb destructor (tcp_wfree).
+ *
+ * Its important tcp_wfree() can be replaced by sock_wfree() in the event skb
+ * needs to be reallocated in a driver.
+ * The invariant being skb->truesize substracted from sk->sk_wmem_alloc
+ *
+ * Since transmit from skb destructor is forbidden, we use a tasklet
+ * to process all sockets that eventually need to send more skbs.
+ * We use one tasklet per cpu, with its own queue of sockets.
+ */
+struct tsq_tasklet {
+	struct tasklet_struct	tasklet;
+	struct list_head	head; /* queue of tcp sockets */
+};
+static DEFINE_PER_CPU(struct tsq_tasklet, tsq_tasklet);
+
+/*
+ * One tasklest per cpu tries to send more skbs.
+ * We run in tasklet context but need to disable irqs when
+ * transfering tsq->head because tcp_wfree() might
+ * interrupt us (non NAPI drivers)
+ */
+static void tcp_tasklet_func(unsigned long data)
+{
+	struct tsq_tasklet *tsq = (struct tsq_tasklet *)data;
+	LIST_HEAD(list);
+	unsigned long flags;
+	struct list_head *q, *n;
+	struct tcp_sock *tp;
+	struct sock *sk;
+
+	local_irq_save(flags);
+	list_splice_init(&tsq->head, &list);
+	local_irq_restore(flags);
+
+	list_for_each_safe(q, n, &list) {
+		tp = list_entry(q, struct tcp_sock, tsq_node);
+		list_del(&tp->tsq_node);
+
+		sk = (struct sock *)tp;
+		bh_lock_sock(sk);
+
+		if (!sock_owned_by_user(sk)) {
+			if ((1 << sk->sk_state) &
+			    (TCPF_ESTABLISHED | TCPF_FIN_WAIT1 |
+			     TCPF_CLOSING | TCPF_CLOSE_WAIT))
+				tcp_write_xmit(sk,
+					       tcp_current_mss(sk),
+					       0, 0,
+					       GFP_ATOMIC);
+		} else {
+			/* defer the work to tcp_release_cb() */
+			set_bit(TSQ_OWNED, &tp->tsq_flags);
+		}
+		bh_unlock_sock(sk);
+
+		clear_bit(TSQ_QUEUED, &tp->tsq_flags);
+		sk_free(sk);
+	}
+}
+
+/**
+ * tcp_release_cb - tcp release_sock() callback
+ * @sk: socket
+ *
+ * called from release_sock() to perform protocol dependent
+ * actions before socket release.
+ */
+void tcp_release_cb(struct sock *sk)
+{
+	struct tcp_sock *tp = tcp_sk(sk);
+
+	if (test_and_clear_bit(TSQ_OWNED, &tp->tsq_flags)) {
+		if ((1 << sk->sk_state) &
+		    (TCPF_ESTABLISHED | TCPF_FIN_WAIT1 |
+		     TCPF_CLOSING | TCPF_CLOSE_WAIT))
+			tcp_write_xmit(sk,
+				       tcp_current_mss(sk),
+				       0, 0,
+				       GFP_ATOMIC);
+	}
+}
+EXPORT_SYMBOL(tcp_release_cb);
+
+void __init tcp_tasklet_init(void)
+{
+	int i;
+
+	for_each_possible_cpu(i) {
+		struct tsq_tasklet *tsq = &per_cpu(tsq_tasklet, i);
+
+		INIT_LIST_HEAD(&tsq->head);
+		tasklet_init(&tsq->tasklet,
+			     tcp_tasklet_func,
+			     (unsigned long)tsq);
+	}
+}
+
+/*
+ * Write buffer destructor automatically called from kfree_skb.
+ * We cant xmit new skbs from this context, as we might already
+ * hold qdisc lock.
+ */
+void tcp_wfree(struct sk_buff *skb)
+{
+	struct sock *sk = skb->sk;
+	struct tcp_sock *tp = tcp_sk(sk);
+
+	if (test_and_clear_bit(TSQ_THROTTLED, &tp->tsq_flags) &&
+	    !test_and_set_bit(TSQ_QUEUED, &tp->tsq_flags)) {
+		unsigned long flags;
+		struct tsq_tasklet *tsq;
+
+		/* Keep a ref on socket.
+		 * This last ref will be released in tcp_tasklet_func()
+		 */
+		atomic_sub(skb->truesize - 1, &sk->sk_wmem_alloc);
+
+		/* queue this socket to tasklet queue */
+		local_irq_save(flags);
+		tsq = &__get_cpu_var(tsq_tasklet);
+		list_add(&tp->tsq_node, &tsq->head);
+		tasklet_schedule(&tsq->tasklet);
+		local_irq_restore(flags);
+	} else {
+		sock_wfree(skb);
+	}
+}
+
 /* This routine actually transmits TCP packets queued in by
  * tcp_do_sendmsg().  This is used by both the initial
  * transmission and possible later retransmissions.
@@ -844,7 +983,12 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
 
 	skb_push(skb, tcp_header_size);
 	skb_reset_transport_header(skb);
-	skb_set_owner_w(skb, sk);
+
+	skb_orphan(skb);
+	skb->sk = sk;
+	skb->destructor = (sysctl_tcp_limit_output_bytes > 0) ?
+			  tcp_wfree : sock_wfree;
+	atomic_add(skb->truesize, &sk->sk_wmem_alloc);
 
 	/* Build TCP header and checksum it. */
 	th = tcp_hdr(skb);
@@ -1780,6 +1924,7 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
 	while ((skb = tcp_send_head(sk))) {
 		unsigned int limit;
 
+
 		tso_segs = tcp_init_tso_segs(sk, skb, mss_now);
 		BUG_ON(!tso_segs);
 
@@ -1800,6 +1945,13 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
 				break;
 		}
 
+		/* TSQ : sk_wmem_alloc accounts skb truesize,
+		 * including skb overhead. But thats OK.
+		 */
+		if (atomic_read(&sk->sk_wmem_alloc) >= sysctl_tcp_limit_output_bytes) {
+			set_bit(TSQ_THROTTLED, &tp->tsq_flags);
+			break;
+		}
 		limit = mss_now;
 		if (tso_segs > 1 && !tcp_urg_mode(tp))
 			limit = tcp_mss_split_point(sk, skb, mss_now,
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 61175cb2478..70458a9cd83 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1970,6 +1970,7 @@ struct proto tcpv6_prot = {
 	.sendmsg		= tcp_sendmsg,
 	.sendpage		= tcp_sendpage,
 	.backlog_rcv		= tcp_v6_do_rcv,
+	.release_cb		= tcp_release_cb,
 	.hash			= tcp_v6_hash,
 	.unhash			= inet_unhash,
 	.get_port		= inet_csk_get_port,
-- 
cgit v1.2.3-70-g09d2


From 2100c8d2d9db23c0a09901a782bb4e3b21bee298 Mon Sep 17 00:00:00 2001
From: Yuchung Cheng <ycheng@google.com>
Date: Thu, 19 Jul 2012 06:43:05 +0000
Subject: net-tcp: Fast Open base

This patch impelements the common code for both the client and server.

1. TCP Fast Open option processing. Since Fast Open does not have an
   option number assigned by IANA yet, it shares the experiment option
   code 254 by implementing draft-ietf-tcpm-experimental-options
   with a 16 bits magic number 0xF989. This enables global experiments
   without clashing the scarce(2) experimental options available for TCP.

   When the draft status becomes standard (maybe), the client should
   switch to the new option number assigned while the server supports
   both numbers for transistion.

2. The new sysctl tcp_fastopen

3. A place holder init function

Signed-off-by: Yuchung Cheng <ycheng@google.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/tcp.h        | 10 ++++++++++
 include/net/tcp.h          |  9 ++++++++-
 net/ipv4/Makefile          |  2 +-
 net/ipv4/syncookies.c      |  2 +-
 net/ipv4/sysctl_net_ipv4.c |  7 +++++++
 net/ipv4/tcp_fastopen.c    | 11 +++++++++++
 net/ipv4/tcp_input.c       | 26 ++++++++++++++++++++++----
 net/ipv4/tcp_ipv4.c        |  2 +-
 net/ipv4/tcp_minisocks.c   |  4 ++--
 net/ipv4/tcp_output.c      | 25 +++++++++++++++++++++----
 net/ipv6/syncookies.c      |  2 +-
 net/ipv6/tcp_ipv6.c        |  2 +-
 12 files changed, 86 insertions(+), 16 deletions(-)
 create mode 100644 net/ipv4/tcp_fastopen.c

(limited to 'net/ipv4/tcp_minisocks.c')

diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index 1888169e07c..12948f54383 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -243,6 +243,16 @@ static inline unsigned int tcp_optlen(const struct sk_buff *skb)
 	return (tcp_hdr(skb)->doff - 5) * 4;
 }
 
+/* TCP Fast Open */
+#define TCP_FASTOPEN_COOKIE_MIN	4	/* Min Fast Open Cookie size in bytes */
+#define TCP_FASTOPEN_COOKIE_MAX	16	/* Max Fast Open Cookie size in bytes */
+
+/* TCP Fast Open Cookie as stored in memory */
+struct tcp_fastopen_cookie {
+	s8	len;
+	u8	val[TCP_FASTOPEN_COOKIE_MAX];
+};
+
 /* This defines a selective acknowledgement block. */
 struct tcp_sack_block_wire {
 	__be32	start_seq;
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 85c5090bfe2..5aed3718fde 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -170,6 +170,11 @@ extern void tcp_time_wait(struct sock *sk, int state, int timeo);
 #define TCPOPT_TIMESTAMP	8	/* Better RTT estimations/PAWS */
 #define TCPOPT_MD5SIG		19	/* MD5 Signature (RFC2385) */
 #define TCPOPT_COOKIE		253	/* Cookie extension (experimental) */
+#define TCPOPT_EXP		254	/* Experimental */
+/* Magic number to be after the option value for sharing TCP
+ * experimental options. See draft-ietf-tcpm-experimental-options-00.txt
+ */
+#define TCPOPT_FASTOPEN_MAGIC	0xF989
 
 /*
  *     TCP option lengths
@@ -180,6 +185,7 @@ extern void tcp_time_wait(struct sock *sk, int state, int timeo);
 #define TCPOLEN_SACK_PERM      2
 #define TCPOLEN_TIMESTAMP      10
 #define TCPOLEN_MD5SIG         18
+#define TCPOLEN_EXP_FASTOPEN_BASE  4
 #define TCPOLEN_COOKIE_BASE    2	/* Cookie-less header extension */
 #define TCPOLEN_COOKIE_PAIR    3	/* Cookie pair header extension */
 #define TCPOLEN_COOKIE_MIN     (TCPOLEN_COOKIE_BASE+TCP_COOKIE_MIN)
@@ -222,6 +228,7 @@ extern int sysctl_tcp_retries1;
 extern int sysctl_tcp_retries2;
 extern int sysctl_tcp_orphan_retries;
 extern int sysctl_tcp_syncookies;
+extern int sysctl_tcp_fastopen;
 extern int sysctl_tcp_retrans_collapse;
 extern int sysctl_tcp_stdurg;
 extern int sysctl_tcp_rfc1337;
@@ -418,7 +425,7 @@ extern int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 		       size_t len, int nonblock, int flags, int *addr_len);
 extern void tcp_parse_options(const struct sk_buff *skb,
 			      struct tcp_options_received *opt_rx, const u8 **hvpp,
-			      int estab);
+			      int estab, struct tcp_fastopen_cookie *foc);
 extern const u8 *tcp_parse_md5sig_option(const struct tcphdr *th);
 
 /*
diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile
index a677d804e53..ae2ccf2890e 100644
--- a/net/ipv4/Makefile
+++ b/net/ipv4/Makefile
@@ -7,7 +7,7 @@ obj-y     := route.o inetpeer.o protocol.o \
 	     ip_output.o ip_sockglue.o inet_hashtables.o \
 	     inet_timewait_sock.o inet_connection_sock.o \
 	     tcp.o tcp_input.o tcp_output.o tcp_timer.o tcp_ipv4.o \
-	     tcp_minisocks.o tcp_cong.o tcp_metrics.o \
+	     tcp_minisocks.o tcp_cong.o tcp_metrics.o tcp_fastopen.o \
 	     datagram.o raw.o udp.o udplite.o \
 	     arp.o icmp.o devinet.o af_inet.o  igmp.o \
 	     fib_frontend.o fib_semantics.o fib_trie.o \
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index eab2a7fb15d..650e1528e1e 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -293,7 +293,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb,
 
 	/* check for timestamp cookie support */
 	memset(&tcp_opt, 0, sizeof(tcp_opt));
-	tcp_parse_options(skb, &tcp_opt, &hash_location, 0);
+	tcp_parse_options(skb, &tcp_opt, &hash_location, 0, NULL);
 
 	if (!cookie_check_timestamp(&tcp_opt, &ecn_ok))
 		goto out;
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 3f6a1e762e9..5840c325572 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -366,6 +366,13 @@ static struct ctl_table ipv4_table[] = {
 		.proc_handler	= proc_dointvec
 	},
 #endif
+	{
+		.procname	= "tcp_fastopen",
+		.data		= &sysctl_tcp_fastopen,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
 	{
 		.procname	= "tcp_tw_recycle",
 		.data		= &tcp_death_row.sysctl_tw_recycle,
diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c
new file mode 100644
index 00000000000..a7f729c409d
--- /dev/null
+++ b/net/ipv4/tcp_fastopen.c
@@ -0,0 +1,11 @@
+#include <linux/init.h>
+#include <linux/kernel.h>
+
+int sysctl_tcp_fastopen;
+
+static int __init tcp_fastopen_init(void)
+{
+	return 0;
+}
+
+late_initcall(tcp_fastopen_init);
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index fdd49f1b7a5..a06bb8959e7 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -3732,7 +3732,8 @@ old_ack:
  * the fast version below fails.
  */
 void tcp_parse_options(const struct sk_buff *skb, struct tcp_options_received *opt_rx,
-		       const u8 **hvpp, int estab)
+		       const u8 **hvpp, int estab,
+		       struct tcp_fastopen_cookie *foc)
 {
 	const unsigned char *ptr;
 	const struct tcphdr *th = tcp_hdr(skb);
@@ -3839,8 +3840,25 @@ void tcp_parse_options(const struct sk_buff *skb, struct tcp_options_received *o
 					break;
 				}
 				break;
-			}
 
+			case TCPOPT_EXP:
+				/* Fast Open option shares code 254 using a
+				 * 16 bits magic number. It's valid only in
+				 * SYN or SYN-ACK with an even size.
+				 */
+				if (opsize < TCPOLEN_EXP_FASTOPEN_BASE ||
+				    get_unaligned_be16(ptr) != TCPOPT_FASTOPEN_MAGIC ||
+				    foc == NULL || !th->syn || (opsize & 1))
+					break;
+				foc->len = opsize - TCPOLEN_EXP_FASTOPEN_BASE;
+				if (foc->len >= TCP_FASTOPEN_COOKIE_MIN &&
+				    foc->len <= TCP_FASTOPEN_COOKIE_MAX)
+					memcpy(foc->val, ptr + 2, foc->len);
+				else if (foc->len != 0)
+					foc->len = -1;
+				break;
+
+			}
 			ptr += opsize-2;
 			length -= opsize;
 		}
@@ -3882,7 +3900,7 @@ static bool tcp_fast_parse_options(const struct sk_buff *skb,
 		if (tcp_parse_aligned_timestamp(tp, th))
 			return true;
 	}
-	tcp_parse_options(skb, &tp->rx_opt, hvpp, 1);
+	tcp_parse_options(skb, &tp->rx_opt, hvpp, 1, NULL);
 	return true;
 }
 
@@ -5637,7 +5655,7 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
 	struct tcp_cookie_values *cvp = tp->cookie_values;
 	int saved_clamp = tp->rx_opt.mss_clamp;
 
-	tcp_parse_options(skb, &tp->rx_opt, &hash_location, 0);
+	tcp_parse_options(skb, &tp->rx_opt, &hash_location, 0, NULL);
 
 	if (th->ack) {
 		/* rfc793:
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index d7d2fa50f07..01aa77a9702 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1307,7 +1307,7 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
 	tcp_clear_options(&tmp_opt);
 	tmp_opt.mss_clamp = TCP_MSS_DEFAULT;
 	tmp_opt.user_mss  = tp->rx_opt.user_mss;
-	tcp_parse_options(skb, &tmp_opt, &hash_location, 0);
+	tcp_parse_options(skb, &tmp_opt, &hash_location, 0, NULL);
 
 	if (tmp_opt.cookie_plus > 0 &&
 	    tmp_opt.saw_tstamp &&
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index c66f2ede160..5912ac3fd24 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -97,7 +97,7 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb,
 
 	tmp_opt.saw_tstamp = 0;
 	if (th->doff > (sizeof(*th) >> 2) && tcptw->tw_ts_recent_stamp) {
-		tcp_parse_options(skb, &tmp_opt, &hash_location, 0);
+		tcp_parse_options(skb, &tmp_opt, &hash_location, 0, NULL);
 
 		if (tmp_opt.saw_tstamp) {
 			tmp_opt.ts_recent	= tcptw->tw_ts_recent;
@@ -534,7 +534,7 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
 
 	tmp_opt.saw_tstamp = 0;
 	if (th->doff > (sizeof(struct tcphdr)>>2)) {
-		tcp_parse_options(skb, &tmp_opt, &hash_location, 0);
+		tcp_parse_options(skb, &tmp_opt, &hash_location, 0, NULL);
 
 		if (tmp_opt.saw_tstamp) {
 			tmp_opt.ts_recent = req->ts_recent;
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 15a7c7bc3e5..4849be76ccd 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -385,15 +385,17 @@ static inline bool tcp_urg_mode(const struct tcp_sock *tp)
 #define OPTION_MD5		(1 << 2)
 #define OPTION_WSCALE		(1 << 3)
 #define OPTION_COOKIE_EXTENSION	(1 << 4)
+#define OPTION_FAST_OPEN_COOKIE	(1 << 8)
 
 struct tcp_out_options {
-	u8 options;		/* bit field of OPTION_* */
+	u16 options;		/* bit field of OPTION_* */
+	u16 mss;		/* 0 to disable */
 	u8 ws;			/* window scale, 0 to disable */
 	u8 num_sack_blocks;	/* number of SACK blocks to include */
 	u8 hash_size;		/* bytes in hash_location */
-	u16 mss;		/* 0 to disable */
-	__u32 tsval, tsecr;	/* need to include OPTION_TS */
 	__u8 *hash_location;	/* temporary pointer, overloaded */
+	__u32 tsval, tsecr;	/* need to include OPTION_TS */
+	struct tcp_fastopen_cookie *fastopen_cookie;	/* Fast open cookie */
 };
 
 /* The sysctl int routines are generic, so check consistency here.
@@ -442,7 +444,7 @@ static u8 tcp_cookie_size_check(u8 desired)
 static void tcp_options_write(__be32 *ptr, struct tcp_sock *tp,
 			      struct tcp_out_options *opts)
 {
-	u8 options = opts->options;	/* mungable copy */
+	u16 options = opts->options;	/* mungable copy */
 
 	/* Having both authentication and cookies for security is redundant,
 	 * and there's certainly not enough room.  Instead, the cookie-less
@@ -564,6 +566,21 @@ static void tcp_options_write(__be32 *ptr, struct tcp_sock *tp,
 
 		tp->rx_opt.dsack = 0;
 	}
+
+	if (unlikely(OPTION_FAST_OPEN_COOKIE & options)) {
+		struct tcp_fastopen_cookie *foc = opts->fastopen_cookie;
+
+		*ptr++ = htonl((TCPOPT_EXP << 24) |
+			       ((TCPOLEN_EXP_FASTOPEN_BASE + foc->len) << 16) |
+			       TCPOPT_FASTOPEN_MAGIC);
+
+		memcpy(ptr, foc->val, foc->len);
+		if ((foc->len & 3) == 2) {
+			u8 *align = ((u8 *)ptr) + foc->len;
+			align[0] = align[1] = TCPOPT_NOP;
+		}
+		ptr += (foc->len + 3) >> 2;
+	}
 }
 
 /* Compute TCP options for SYN packets. This is not the final
diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c
index 7bf3cc427c2..bb46061c813 100644
--- a/net/ipv6/syncookies.c
+++ b/net/ipv6/syncookies.c
@@ -177,7 +177,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
 
 	/* check for timestamp cookie support */
 	memset(&tcp_opt, 0, sizeof(tcp_opt));
-	tcp_parse_options(skb, &tcp_opt, &hash_location, 0);
+	tcp_parse_options(skb, &tcp_opt, &hash_location, 0, NULL);
 
 	if (!cookie_check_timestamp(&tcp_opt, &ecn_ok))
 		goto out;
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index c9dabdd832d..0302ec3fecf 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1033,7 +1033,7 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
 	tcp_clear_options(&tmp_opt);
 	tmp_opt.mss_clamp = IPV6_MIN_MTU - sizeof(struct tcphdr) - sizeof(struct ipv6hdr);
 	tmp_opt.user_mss = tp->rx_opt.user_mss;
-	tcp_parse_options(skb, &tmp_opt, &hash_location, 0);
+	tcp_parse_options(skb, &tmp_opt, &hash_location, 0, NULL);
 
 	if (tmp_opt.cookie_plus > 0 &&
 	    tmp_opt.saw_tstamp &&
-- 
cgit v1.2.3-70-g09d2